Papers › iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse...

iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform

4 Mar 2022arXiv:2203.02395archive 2025-07-28

Takuhiro Kaneko, Kou Tanaka, Hirokazu Kameoka, Shogo Seki

In recent text-to-speech synthesis and voice conversion systems, a mel-spectrogram is commonly applied as an intermediate representation, and the necessity for a mel-spectrogram vocoder is increasing. A mel-spectrogram vocoder must solve three inverse problems: recovery of the original-scale magnitude spectrogram, phase reconstruction, and frequency-to-time conversion. A typical convolutional mel-spectrogram vocoder solves these problems jointly and implicitly using a convolutional neural network, including temporal upsampling layers, when directly calculating a raw waveform. Such an approach allows skipping redundant processes during waveform synthesis (e.g., the direct reconstruction of high-dimensional original-scale spectrograms). By contrast, the approach solves all problems in a black box and cannot effectively employ the time-frequency structures existing in a mel-spectrogram. We thus propose iSTFTNet, which replaces some output-side layers of the mel-spectrogram vocoder with the inverse short-time Fourier transform (iSTFT) after sufficiently reducing the frequency dimension using upsampling layers, reducing the computational cost from black-box modeling and avoiding redundant estimations of high-dimensional spectrograms. During our experiments, we applied our ideas to three HiFi-GAN variants and made the models faster and more lightweight with a reasonable speech quality. Audio samples are available at https://www.kecl.ntt.co.jp/people/kaneko.takuhiro/projects/istftnet/.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2203.02395")

Code

Syntology Ran 8 of 11 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 1 ran · honoured contract; 3 ran · our draft was wrong; 4 ran with no contract checked.

By repository: community (archive-listed): 11 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

hcy71o/autovocoder mentioned on GitHubpytorchApache-2.0 report
rishikksh20/iSTFTNet-pytorch mentioned on GitHubpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

11 samples harvested; 8 ran; 1 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
3ran · our draft was wrong
4ran
3unverified

Licence: 0 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from hcy71o/autovocoder. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

load_checkpoint hcy71o/autovocoder/inference.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · 1644a2f2942ffe4c · report
discriminator_loss hcy71o/autovocoder/models.py community (archive-listed) ran Apache-2.0 (permissive) · 7137577cbef51217 · report
feature_loss hcy71o/autovocoder/models.py community (archive-listed) ran Apache-2.0 (permissive) · e453b51f0ed5fb28 · report
generator_loss hcy71o/autovocoder/models.py community (archive-listed) ran Apache-2.0 (permissive) · 1a9d74439d969cfd · report
get_padding hcy71o/autovocoder/utils.py community (archive-listed) ran · honoured contract fingerprinted Apache-2.0 (permissive) · a26f85d7c72ef39a · report
load_checkpoint hcy71o/autovocoder/utils.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · 19c9fe23dc000c61 · report
load_wav hcy71o/autovocoder/complexdataset.py community (archive-listed) ran Apache-2.0 (permissive) · 8043eaefe4c09c1f · report
scan_checkpoint hcy71o/autovocoder/inference.py community (archive-listed) ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 404632cb4f4669da · report
dynamic_range_compression hcy71o/autovocoder/complexdataset.py community (archive-listed) unverified Apache-2.0 (permissive) · be031b15a988a556 · report
dynamic_range_decompression hcy71o/autovocoder/complexdataset.py community (archive-listed) unverified Apache-2.0 (permissive) · 9e30e7d510c9d341 · report
plot_spectrogram hcy71o/autovocoder/utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 8520e6e61b8bf789 · report

Tasks

Speech SynthesisText to SpeechText-To-Speech SynthesisVoice Conversiontext-to-speech

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

HiFi-GAN

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections